Archived Events

Gilead-Berkeley Global Health Equity and Innovation (GHEI) Panel Recap

On Wednesday, November 20th, the Berkeley Public Health community gathered for an insightful panel discussion, Harnessing Academic-Industry Partnerships to Address Public Health Challenges and Infectious Disease Threats: Innovating Health Solutions and Envisioning Change Through Public-Private Collaboration. The event featured experts exploring how collaborative efforts between academia and industry can drive innovative solutions in global health.

Special thanks to our esteemed moderator, Art Reingold from the UC Berkeley School of Public Health, and our panelists—Mark van...

11/13/24 Series: "Unleashing Sparse Regularization: Equation for Setting Regularization Strength to Achieve Targeted Compression in CNNs and Transformers"

Join us on November 13th for another exciting talk in our Fall 2024 CTML Seminar Series! Gilmer Valdes’ talk “Unleashing Sparse Regularization: Equation for Setting Regularization Strength to Achieve Targeted Compression in CNNs and Transformers ” will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.


Setting the regularization strength parameter in neural networks is often done manually, requiring computationally heavy grid searches that limit practitioners to testing only a few values. This constraint hinders fully harnessing sparse regularization’...

11/6/24 Seminar: "Optimizing Variance Estimation for Causal Inference Through HAL-based Bootstrap"

Join us on November 6th to continue our Fall 2024 CTML Seminar Series! Wendy Ji's talk "Optimizing Variance Estimation for Causal Inference Through HAL-based Bootstrap" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

Variance estimation plays a critical role in accurately inferring causal parameters. Conventional approaches often underestimate variance, potentially leading to elevated type-I errors in limited samples or presence of near-positivity violations. By combining novel variance estimators with a HAL-based bootstrap approach, this project seeks to...

10/30/24 Seminar: "Towards a Post-Market Monitoring Framework for Machine Learning-Based Medical Devices"

Join us on October 30th for another exciting talk in our Fall 2024 CTML Seminar Series! Jean Feng's talk "Towards a Post-Market Monitoring Framework for Machine Learning-Based Medical Devices" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

After a machine learning (ML)-based system is deployed in clinical practice, performance monitoring is widely recognized to be a crucial component to ensuring the safety and effectiveness of the algorithm over time. Nevertheless, designing an effective monitoring strategy is highly complex given the multitude of design...

10/23/24 Seminar: "Embedded RCTs in Learning Health Systems"

Join us on October 23rd to continue our Fall 2024 CTML Seminar Series. Mark Pletcher's talk "Embedded RCTs in Learning Health Systems" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

By embedding randomization into the process of healthcare delivery and comparing outcomes of patients randomly exposed to an intervention or an alternative, health systems can learn to improve the care they deliver and the outcomes of their patients. Embedding randomization into healthcare delivery, however, is challenging. Randomization must be triggered for the right patient at...

10/16/24 Seminar: "Towards Estimation of the Intensity"

Join us on October 16th to continue our Fall 2024 CTML Seminar Series! Yi Li's talk "Towards Estimation of the Intensity" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5101. Please note the conference room change for this seminar.

Intensity estimation serves as a key building block to understand the jumping process. In statistics, we can even model the density through intensity. However, intensity estimation usually involves partial log likelihood that takes the form of integration of the intensity and log of the intensity itself for a single observation of...

10/9/24 Seminar: "Integrated Multi-Omics Analysis of Human Milk, Maternal Nutritional Supplementation, and Child Growth: Results from the IMiC Multi-Site Study"

Join us on October 9th to continue our Fall 2024 CTML Seminar Series! Andrew Merten's talk "Integrated Multi-Omics Analysis of Human Milk, Maternal Nutritional Supplementation, and Child Growth: Results from the IMiC Multi-Site Study" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

Breastfeeding provides optimal nutrition and immune protection to infants. Human milk contains a plethora of nutritional and non-nutritional compounds that support infant growth and development. Many are highly variable between and within mothers, but little is known about the source...

10/2/24 Seminar: "Causal Inference for Evaluating the Effectiveness of Medical Tests"

Join us on October 2nd to continue our Fall 2024 CTML Seminar Series. Wenxin Zhang's talk "Causal Inference for Evaluating the Effectiveness of Medical Tests" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

Medical tests play a critical role in detecting, diagnosing, and monitoring diseases. However, unlike treatments, administering medical tests does not directly influence health outcomes. This disconnection poses a challenge in evaluating their true effectiveness. In this...

9/18/24 Seminar: "Towards More Accurate, Reliable and Equitable Pulse Oximetry"

Join us on September 18 for another amazing talk in our Fall 2024 CTML Seminar Series. Tianyue Zhou's talk "Towards More Accurate, Reliable and Equitable Pulse Oximetry" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

In this talk, I will first give an overview of pulse oximetry. Then I will focus on one major issue in this field: bias due to skin pigmentation. In particular, I will discuss how we (as biostatisticians) could help address this problem. Preliminary results will be provided.

9/11/24 Seminar: "Integrative Deep Multi-Learning for Predicting and Biclustering Cancer Drug Responses (impaCluster): Leveraging Omics and Drug Molecular Data"

Join us on September 11 to kick off our Fall 2024 CTML Seminar Series. Seraphina Shi's talk "Integrative Deep Multi-Learning for Predicting and Biclustering Cancer Drug Responses (impaCluster): Leveraging Omics and Drug Molecular Data" will take place at 11:00AM at Berkeley Way West, 5th Floor, Room 5401.

Precision medicine in cancer treatment leverages complex relationships between cancer genetics and drug structures, addressed by 'impaCluster'. In this talk, I will introduce impaCluster, which integrates deep multi-task prediction and biclustering to identify sensitive subsets of...